b4027

cuda : clear error after changing peer access (#10153)

b4024

CANN: adjust backend registry refactor. (#10158)

remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.

b4023

sync : ggml

b4020

ggml : move CPU backend to a separate file (#10144)

b4019

metal : minor fixup in FA kernel (#10143)

* metal : minor fixup in FA kernel

ggml-ci

* metal : use the unrolled loop variable

* metal : remove unused var

b4016

server : fix slot selection by lru (#10126)

* server : fix slot selection by lru, migrate lcs to `size_t`

* minor debug log fix

b4014

llama : adjust default context size + print warnings (#10136)

* llama : adjust default context size + print warnings

ggml-ci

* ggml-ci : add missing gpu-layers + adjust context sizes

b4013

simple-chat : only add bos on first prompt (#10129)

b4011

llama : add simple-chat example (#10124)

* llama : add simple-chat example

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

b4009

vulkan : improve ggml_vk_create_buffer error handling (#9898)